MIT IAP short course: Matrix Calculus for Machine Learning and Beyond

Transductive regular expressions

C compiler (mirror)

Brzozowski derivative python sketch

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

vim mode for editing metamath files

Finite state transducer library. Minimalistic pure C implementation.

terminal telegram client

Sandbox for training deep learning networks

Accelerated deep learning R&D

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKT…

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

Pixel-wise segmentation on VOC2012 dataset using pytorch.

Benchmarks for several RNN variations with different deep-learning frameworks

This library provides common speech features for ASR including MFCCs and filterbank energies.

Theano-based implementation of Deep Q-learning

Neural net code for lexicon-free speech recognition with connectionist temporal classification

A flexible framework of neural networks for deep learning

Python module for performing basic dense linear algebra computations on the GPU using CUDA.

Demonstration of recurrent neural network implemented with Theano